A precise localization system and a map that properly represents the environment are fundamental for several robotic applications. Traditional LiDAR SLAM algorithms are particularly susceptible to underestimating the distance covered by real robots in environments with few geometric features. Common industrial confined spaces, such as ducts and galleries, have long and homogeneous structures, which are difficult to map. In this paper, we propose a novel approach, the EKF-LOAM, which fuses wheel odometry and IMU (Inertial Measurement Unit) data into the LeGO-LOAM algorithm using an Extended Kalman Filter. For that, the EKF-LOAM uses a simple and lightweight adaptive covariance matrix based on the number of detected geometric features. Simulated and real-world experiments with the EspeleoRobô, a service robot designed to inspect confined places, show that the EKF-LOAM method reduces the underestimating problem, with improvements greater than 50% when compared to the original LeGO-LOAM algorithm. Note to Practitioners—This paper is motivated by the challenges of autonomous navigation for mobile ground robots within confined and unstructured environments. Here, we propose a data fusion framework that uses common sensors (such as LiDARs, wheel odometry, and inertial devices) to improve the simultaneous localization and mapping (SLAM) capabilities of a robot without GPS and compass. This approach does not need artificial landmarks nor ideal light and, in scenarios with few geometric features, increases the performance of LiDAR SLAM techniques based on edge and planar features. We also provide a robust controller for the autonomous navigation of the robot during the mapping of a tunnel. Experiments carried out in simulation and real-world confined places show the effectiveness of our approach. In future work, we shall incorporate other sensors, such as cameras, to improve the SLAM process.

中文翻译：

---

EKF-LOAM：激光雷达 SLAM 与车轮里程计和惯性数据的自适应融合，适用于几何特征很少的有限空间


精确的定位系统和正确表示环境的地图是多种机器人应用的基础。传统的 LiDAR SLAM 算法特别容易低估真实机器人在几何特征很少的环境中所覆盖的距离。常见的工业密闭空间，例如管道和画廊，具有长而均匀的结构，很难绘制地图。在本文中，我们提出了一种新颖的方法 EKF-LOAM，它使用扩展卡尔曼滤波器将车轮里程计和 IMU（惯性测量单元）数据融合到 LeGO-LOAM 算法中。为此，EKF-LOAM 基于检测到的几何特征的数量使用简单且轻量级的自适应协方差矩阵。 EspeleoRobô（一种设计用于检查密闭空间的服务机器人）的模拟和实际实验表明，EKF-LOAM 方法减少了低估问题，与原始 LeGO-LOAM 算法相比，改进超过 50%。从业者须知——本文的动机是移动地面机器人在受限和非结构化环境中自主导航的挑战。在这里，我们提出了一种数据融合框架，该框架使用常见传感器（例如激光雷达、车轮测距仪和惯性设备）来提高没有 GPS 和指南针的机器人的同步定位和建图（SLAM）能力。这种方法不需要人工地标，也不需要理想的光线，并且在几何特征很少的场景中，可以提高基于边缘和平面特征的 LiDAR SLAM 技术的性能。我们还提供了一个强大的控制器，用于在隧道测绘过程中机器人的自主导航。 在模拟和现实世界的有限空间中进行的实验表明了我们方法的有效性。在未来的工作中，我们将结合其他传感器（例如相机）来改进 SLAM 过程。